A practical approach to determining critical macroeconomic factors inair-traffic volume based on K-means clustering anddecision-tree classification
一种确定关键宏观经济因素的实用方法基于K-means聚类和决策树分类


A given region’s volume of air passengers and cargo is frequently taken to represent its economic development.This research proposes a practical methodology for investigating the inherent patterns of the relationships between air-traffic volume and macroeconomic development, utilizing data-mining techniques, including K-meansclustering and Decision Tree C5.0 classification. Using the case of Taiwan from 2001 to 2014, 32 potentialmacroeconomic factors ascertained from a literature review were combined with air-traffic volume data toestablish a 168-month dataset. After this dataset was grouped into five clusters, decision trees were implementedto determine its critical macroeconomic characteristics. The resulting four critical factors and their thresholdswere the Information and Electronics Industrial Production Index (IE Index), at 83.22; National Income PerCapita, at US$3,222; Employed Population, at 10.134 million; and the Japanese Nikkei 225 Stock Average, at10564.44. Among these, the IE Index was found to be the first critical factor relating to air-traffic volume as wellas the only characteristic to distinguish Cluster V – 58 consecutive months from March 2010 to December 2014inclusive – among others, and the reasonableness of this finding was confirmed via examination of detailed airtraffic statistics. Besides, the effectiveness of the four identified critical factors as predictive variables werevalidated by comparing forecasted results with actual air traffic volume from 2015 to 2016. Understanding thesefour critical factors and their relative importance is of great value to policymakers seeking to allocate limitedresources optimally and objectively. Therefore, as an effective and efficient means of capturing significant andexplainable macroeconomic factors influencing air-traffic volume, the proposed methodology can be applied tostrategy formulation, operations management, and investment planning by governments, airports, airlines, andrelated entities.

一个特定地区的航空客运量和货运量常常被用来代表该地区的经济发展。
本研究提出一种实用的方法，利用包括K-means在内的数据挖掘技术，来调查航空交通量与宏观经济发展之间关系的内在模式
集群和决策树C5.0分类。
以台湾为例，从2001年到2014年，有32种潜力
从文献综述中确定的宏观经济因素与航空交通量数据相结合
建立一个168个月的数据集。
将该数据集分为5个聚类，实现决策树
来确定其关键的宏观经济特征。
由此产生的四个关键因素及其阈值
为资讯及电子工业生产指数，为83.22;
国民人均收入
人均3222美元;
就业人口1013.4万人;
和日本日经225指数
10564.44。
在这些因素中，IE指数被发现是与航空交通量相关的第一个关键因素
作为区分V - 58星团2010年3月至2014年12月连续几个月的唯一特征
经详细的航空交通统计数字审查，证实这项调查结果的合理性。
此外，四个确定的关键因素作为预测变量的有效性为
通过将预测结果与2015 - 2016年的实际航空交通量进行比较，验证了这一点。
理解这些
四个关键因素及其相对重要性对寻求配置有限资源的政策制定者具有重大价值
资源优化和客观。
因此，作为一种有效且高效的捕捉手段，意义重大
可解释的宏观经济因素影响航空交通量，提出的方法可以应用于
由政府、机场、航空公司和其他机构制定战略、运营管理和投资计划
相关的实体。